Algorithm Affinity Propagation Research Articles

Network Pruning Using Adaptive Exemplar Filters.

Popular network pruning algorithms reduce redundant information by optimizing hand-crafted models, and may cause suboptimal performance and long time in selecting filters. We innovatively introduce adaptive exemplar filters to simplify the algorithm design, resulting in an automatic and efficient pruning approach called EPruner. Inspired by the face recognition community, we use a message-passing algorithm Affinity Propagation on the weight matrices to obtain an adaptive number of exemplars, which then act as the preserved filters. EPruner breaks the dependence on the training data in determining the "important" filters and allows the CPU implementation in seconds, an order of magnitude faster than GPU-based SOTAs. Moreover, we show that the weights of exemplars provide a better initialization for the fine-tuning. On VGGNet-16, EPruner achieves a 76.34%-FLOPs reduction by removing 88.80% parameters, with 0.06% accuracy improvement on CIFAR-10. In ResNet-152, EPruner achieves a 65.12%-FLOPs reduction by removing 64.18% parameters, with only 0.71% top-5 accuracy loss on ILSVRC-2012. Our code is available at https://github.com/lmbxmu/EPruner.

New Binding Mode of SLURP Protein to a7 Nicotinic Acetylcholine Receptor Revealed by Computer Simulations

SLURP-1 is a member of three-finger toxin-like proteins. Their characteristic feature is a set of three beta strands extruding from hydrophobic core stabilized by disulfide bonds. Each beta-strand carries a flexible loop, which is responsible for recognition. SLURP-1 was recently shown to act as an endogenous growth regulator of keratinocytes and tumor suppressor by reducing cell migration and invasion by antagonizing the pro-malignant effects of nicotine. This effect is achieved through allosteric interaction with alpha7 nicotinic acetylcholine receptors (alpha-7 nAChRs) in an antagonist-like manner. Moreover, this interaction is unaffected by several well-known agents specifically alpha-bungarotoxin. In this work, we carry out the conformational analysis of the SLURP-1 by a microsecond-long full-atom explicit solvent molecular dynamics simulations followed by clustering, to identify representative states. To achieve this timescale we employed a GPU-accelerated version of GROMACS modeling package. To avoid human bias in clustering we used a non-parametric clustering algorithm Affinity Propagation adapted for biomolecules and HPC environments. Then, we applied protein-protein molecular docking of the ten most massive clusters to alpha7-nAChRs in order to test if structural variability can affect binding. Docking simulations revealed the unusual binding mode of one of the minor SLURP-1 conformations.

BinSanity: unsupervised clustering of environmental microbial assemblies using coverage and affinity propagation.

Metagenomics has become an integral part of defining microbial diversity in various environments. Many ecosystems have characteristically low biomass and few cultured representatives. Linking potential metabolisms to phylogeny in environmental microorganisms is important for interpreting microbial community functions and the impacts these communities have on geochemical cycles. However, with metagenomic studies there is the computational hurdle of ‘binning’ contigs into phylogenetically related units or putative genomes. Binning methods have been implemented with varying approaches such as k-means clustering, Gaussian mixture models, hierarchical clustering, neural networks, and two-way clustering; however, many of these suffer from biases against low coverage/abundance organisms and closely related taxa/strains. We are introducing a new binning method, BinSanity, that utilizes the clustering algorithm affinity propagation (AP), to cluster assemblies using coverage with compositional based refinement (tetranucleotide frequency and percent GC content) to optimize bins containing multiple source organisms. This separation of composition and coverage based clustering reduces bias for closely related taxa. BinSanity was developed and tested on artificial metagenomes varying in size and complexity. Results indicate that BinSanity has a higher precision, recall, and Adjusted Rand Index compared to five commonly implemented methods. When tested on a previously published environmental metagenome, BinSanity generated high completion and low redundancy bins corresponding with the published metagenome-assembled genomes.

Using affinity propagation for identifying subspecies among clonal organisms: lessons from M. tuberculosis

BackgroundClassification and naming is a key step in the analysis, understanding and adequate management of living organisms. However, where to set limits between groups can be puzzling especially in clonal organisms. Within the Mycobacterium tuberculosis complex (MTC), the etiological agent of tuberculosis (TB), experts have first identified several groups according to their pattern at repetitive sequences, especially at the CRISPR locus (spoligotyping), and to their epidemiological relevance. Most groups such as "Beijing" found good support when tested with other loci. However, other groups such as T family and T1 subfamily (belonging to the "Euro-American" lineage) correspond to non-monophyletic groups and still need to be refined. Here, we propose to use a method called Affinity Propagation that has been successfully used in image categorization to identify relevant patterns at the CRISPR locus in MTC.ResultsTo adequately infer the relative divergence time between strains, we used a distance method inspired by the recent evolutionary model by Reyes et al. We first confirm that this method performs better than the Jaccard index commonly used to compare spoligotype patterns. Second, we document the support of each spoligotype family among the previous classification using affinity propagation on the international spoligotyping database SpolDB4. This allowed us to propose a consensus assignation for all SpolDB4 spoligotypes. Third, we propose new signatures to subclassify the T family.ConclusionAltogether, this study shows how the new clustering algorithm Affinity Propagation can help building or refining clonal organims classifications. It also describes well-supported families and subfamilies among M. tuberculosis complex, especially inside the modern "Euro-American" lineage.

Text Clustering with Seeds Affinity Propagation

Based on an effective clustering algorithm-Affinity Propagation (AP)-we present in this paper a novel semisupervised text clustering algorithm, called Seeds Affinity Propagation (SAP). There are two main contributions in our approach: 1) a new similarity metric that captures the structural information of texts, and 2) a novel seed construction method to improve the semisupervised clustering process. To study the performance of the new algorithm, we applied it to the benchmark data set Reuters-21578 and compared it to two state-of-the-art clustering algorithms, namely, k-means algorithm and the original AP algorithm. Furthermore, we have analyzed the individual impact of the two proposed contributions. Results show that the proposed similarity metric is more effective in text clustering (F-measures ca. 21 percent higher than in the AP algorithm) and the proposed semisupervised strategy achieves both better clustering results and faster convergence (using only 76 percent iterations of the original AP). The complete SAP algorithm obtains higher F-measure (ca. 40 percent improvement over k-means and AP) and lower entropy (ca. 28 percent decrease over k-means and AP), improves significantly clustering execution time (20 times faster) in respect that k-means, and provides enhanced robustness compared with all other methods.

New mutational trends in the HA protein of 2009 H1N1 pandemic influenza virus from May 2010 to February 2011

As we enter the year of 2011, the 2009 H1N1 pandemic influenza virus is in the news again. At least 20 people have died of this virus in China since the beginning of 2011 and it is now the predominant flu strain in the country. Although this novel virus was quite stable during its run in the flu season of 2009-2010, a genetic variant of this virus was found in Singapore in early 2010, and then in Australia and New Zealand during their 2010 winter influenza season. Several critical mutations in the HA protein of this variant were uncovered in the strains collected from January 2010 to April 2010. Moreover, a structural homology model of HA from the A/Brisbane/10/2010(H1N1) strain was made based on the structure of A/California/04/2009 (H1N1). The purpose of this study was to investigate mutations in the HA protein of 2009 H1N1 from sequence data collected worldwide from May 2010 to February 2011. A fundamental problem in bioinformatics and biology is to find the similar gene sequences for a given gene sequence of interest. Here we proposed the inverse problem, i.e., finding the exemplars from a group of related gene sequences. With a clustering algorithm affinity propagation, six exemplars of the HA sequences were identified to represent six clusters. One of the clusters contained strain A/Brisbane/12/2010(H1N1) that only differed from A/Brisbane/10/2010 in the HA sequence at position 449. Based on the sequence identity of the six exemplars, nine mutations in HA were located that could be used to distinguish these six clusters. Finally, we discovered the change of correlation patterns for the HA and NA of 2009 H1N1 as a result of the HA receptor binding specificity switch, revealing the balanced interplay between these two surface proteins of the virus.